精通特征工程

30

｜

第

2

章

... 'data_channel_is_entertainment', 'data_channel_is_bus',

... 'data_channel_is_socmed', 'data_channel_is_tech',

... 'data_channel_is_world']

>>> X = df[features]

>>> y = df[['shares']]

# 创建交互特征对，跳过固定偏移项

>>> X2 = preproc.PolynomialFeatures(include_bias=False).fit_transform(X)

>>> X2.shape

(39644, 170)

# 为两个特征集创建训练集和测试集

>>> X1_train, X1_test, X2_train, X2_test, y_train, y_test = \

... train_test_split(X, X2, y, test_size=0.3, random_state=123)

>>> def evaluate_feature(X_train, X_test, y_train, y_test):

... """Fit a linear regression model on the training set and

... score on the test set"""

... model = linear_model.LinearRegression().fit(X_train, ...